Sébastien M. R. Arnold

Sumedh A Sontakke, Jesse Zhang, Sébastien M. R. Arnold et al.

Reward specification is a notoriously difficult problem in reinforcement learning, requiring extensive expert supervision to design robust reward functions. Imitation learning (IL) methods attempt to circumvent these problems by utilizing expert demonstrations but typically require a large number of in-domain expert demonstrations. Inspired by advances in the field of Video-and-Language Models (VLMs), we present RoboCLIP, an online imitation learning method that uses a single demonstration (overcoming the large data requirement) in the form of a video demonstration or a textual description of the task to generate rewards without manual reward function design. Additionally, RoboCLIP can also utilize out-of-domain demonstrations, like videos of humans solving the task for reward generation, circumventing the need to have the same demonstration and deployment domains. RoboCLIP utilizes pretrained VLMs without any finetuning for reward generation. Reinforcement learning agents trained with RoboCLIP rewards demonstrate 2-3 times higher zero-shot performance than competing imitation learning methods on downstream robot manipulation tasks, doing so using only one video/text demonstration.

Megan M. Baker, Alexander New, Mario Aguilar-Simon et al.

Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed. This critical gap may be addressed through the development of "Lifelong Learning" systems that are capable of 1) Continuous Learning, 2) Transfer and Adaptation, and 3) Scalability. Unfortunately, efforts to improve these capabilities are typically treated as distinct areas of research that are assessed independently, without regard to the impact of each separate capability on other aspects of the system. We instead propose a holistic approach, using a suite of metrics and an evaluation framework to assess Lifelong Learning in a principled way that is agnostic to specific domains or system techniques. Through five case studies, we show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems. We highlight how the proposed suite of metrics quantifies performance trade-offs present during Lifelong Learning system development - both the widely discussed Stability-Plasticity dilemma and the newly proposed relationship between Sample Efficient and Robust Learning. Further, we make recommendations for the formulation and use of metrics to guide the continuing development of Lifelong Learning systems and assess their progress in the future.

Sébastien M. R. Arnold, Fei Sha

We study how to transfer representations pretrained on source tasks to target tasks in visual percept based RL. We analyze two popular approaches: freezing or finetuning the pretrained representations. Empirical studies on a set of popular tasks reveal several properties of pretrained representations. First, finetuning is required even when pretrained representations perfectly capture the information required to solve the target task. Second, finetuned representations improve learnability and are more robust to noise. Third, pretrained bottom layers are task-agnostic and readily transferable to new tasks, while top layers encode task-specific information and require adaptation. Building on these insights, we propose a self-supervised objective that clusters representations according to the policy they induce, as opposed to traditional representation similarity measures which are policy-agnostic (e.g. Euclidean norm, cosine similarity). Together with freezing the bottom layers, this objective results in significantly better representation than frozen, finetuned, and self-supervised alternatives on a wide range of benchmarks.

Sébastien M. R. Arnold, Praateek Mahajan, Debajyoti Datta et al.

Meta-learning researchers face two fundamental issues in their empirical work: prototyping and reproducibility. Researchers are prone to make mistakes when prototyping new algorithms and tasks because modern meta-learning methods rely on unconventional functionalities of machine learning frameworks. In turn, reproducing existing results becomes a tedious endeavour -- a situation exacerbated by the lack of standardized implementations and benchmarks. As a result, researchers spend inordinate amounts of time on implementing software rather than understanding and developing new ideas. This manuscript introduces learn2learn, a library for meta-learning research focused on solving those prototyping and reproducibility issues. learn2learn provides low-level routines common across a wide-range of meta-learning techniques (e.g. meta-descent, meta-reinforcement learning, few-shot learning), and builds standardized interfaces to algorithms and benchmarks on top of them. In releasing learn2learn under a free and open source license, we hope to foster a community around standardized software for meta-learning research.

Sébastien M. R. Arnold, Tsam Kiu Pun, Théo-Tim J. Denisart et al.

We present Shapechanger, a library for transfer reinforcement learning specifically designed for robotic tasks. We consider three types of knowledge transfer---from simulation to simulation, from simulation to real, and from real to real---and a wide range of tasks with continuous states and actions. Shapechanger is under active development and open-sourced at: https://github.com/seba-1511/shapechanger/.

Jin Peng Zhou, Sébastien M. R. Arnold, Nan Ding et al.

Auto-evaluating language models (LMs), i.e., using a grader LM to evaluate the candidate LM, is an appealing way to accelerate the evaluation process and the cost associated with it. But this presents a paradox: how can we trust the grader LM, which is presumably weaker than the candidate LM, to assess problems that are beyond the frontier of the capabilities of either model or both? For instance, today's LMs struggle on graduate-level physics and Olympiad-level math, making them unreliable graders in these domains. We show that providing privileged information -- such as ground-truth solutions or problem-specific guidelines -- improves automated evaluations on such frontier problems. This approach offers two key advantages. First, it expands the range of problems where LMs graders apply. Specifically, weaker models can now rate the predictions of stronger models. Second, privileged information can be used to devise easier variations of challenging problems which improves the separability of different LMs on tasks where their performance is generally low. With this approach, general-purpose LM graders match the state of the art performance on RewardBench, surpassing almost all the specially-tuned models. LM graders also outperform individual human raters on Vibe-Eval, and approach human expert graders on Olympiad-level math problems.

Jinhyuk Lee, Anthony Chen, Zhuyun Dai et al.

Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. Leveraging LCLMs' ability to natively ingest and process entire corpora of information offers numerous advantages. It enhances user-friendliness by eliminating the need for specialized knowledge of tools, provides robust end-to-end modeling that minimizes cascading errors in complex pipelines, and allows for the application of sophisticated prompting techniques across the entire system. To assess this paradigm shift, we introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks. However, LCLMs still face challenges in areas like compositional reasoning that are required in SQL-like tasks. Notably, prompting strategies significantly influence performance, emphasizing the need for continued research as context lengths grow. Overall, LOFT provides a rigorous testing ground for LCLMs, showcasing their potential to supplant existing paradigms and tackle novel tasks as model capabilities scale.

Sebastien M. R. Arnold, Pierre L'Ecuyer, Liyu Chen et al.

Reinforcement learning constantly deals with hard integrals, for example when computing expectations in policy evaluation and policy iteration. These integrals are rarely analytically solvable and typically estimated with the Monte Carlo method, which induces high variance in policy values and gradients. In this work, we propose to replace Monte Carlo samples with low-discrepancy point sets. We combine policy gradient methods with Randomized Quasi-Monte Carlo, yielding variance-reduced formulations of policy gradient and actor-critic algorithms. These formulations are effective for policy evaluation and policy improvement, as they outperform state-of-the-art algorithms on standardized continuous control benchmarks. Our empirical analyses validate the intuition that replacing Monte Carlo with Quasi-Monte Carlo yields significantly more accurate gradient estimates.

Sébastien M. R. Arnold, Guneet S. Dhillon, Avinash Ravichandran et al.

Episodic training is a core ingredient of few-shot learning to train models on tasks with limited labelled data. Despite its success, episodic training remains largely understudied, prompting us to ask the question: what is the best way to sample episodes? In this paper, we first propose a method to approximate episode sampling distributions based on their difficulty. Building on this method, we perform an extensive analysis and find that sampling uniformly over episode difficulty outperforms other sampling schemes, including curriculum and easy-/hard-mining. As the proposed sampling method is algorithm agnostic, we can leverage these insights to improve few-shot learning accuracies across many episodic training algorithms. We demonstrate the efficacy of our method across popular few-shot learning datasets, algorithms, network architectures, and protocols.

Sébastien M. R. Arnold, Fei Sha

Constructing new and more challenging tasksets is a fruitful methodology to analyse and understand few-shot classification methods. Unfortunately, existing approaches to building those tasksets are somewhat unsatisfactory: they either assume train and test task distributions to be identical -- which leads to overly optimistic evaluations -- or take a "worst-case" philosophy -- which typically requires additional human labor such as obtaining semantic class relationships. We propose ATG, a principled clustering method to defining train and test tasksets without additional human knowledge. ATG models train and test task distributions while requiring them to share a predefined amount of information. We empirically demonstrate the effectiveness of ATG in generating tasksets that are easier, in-between, or harder than existing benchmarks, including those that rely on semantic information. Finally, we leverage our generated tasksets to shed a new light on few-shot classification: gradient-based methods -- previously believed to underperform -- can outperform metric-based ones when transfer is most challenging.

Sébastien M. R. Arnold, Shariq Iqbal, Fei Sha

Model-Agnostic Meta-Learning (MAML) and its variants have achieved success in meta-learning tasks on many datasets and settings. On the other hand, we have just started to understand and analyze how they are able to adapt fast to new tasks. For example, one popular hypothesis is that the algorithms learn good representations for transfer, as in multi-task learning. In this work, we contribute by providing a series of empirical and theoretical studies, and discover several interesting yet previously unknown properties of the algorithm. We find MAML adapts better with a deep architecture even if the tasks need only a shallow one (and thus, no representation learning is needed). While echoing previous findings by others that the bottom layers in deep architectures enable representation learning, we also find that upper layers enable fast adaptation by being meta-learned to perform adaptive gradient update when generalizing to new tasks. Motivated by these findings, we study several meta-optimization approaches and propose a new one for learning to optimize adaptively. Those approaches attain stronger performance in meta-learning both shallower and deeper architectures than MAML.

James A. Preiss, Sébastien M. R. Arnold, Chen-Yu Wei et al.

We study the variance of the REINFORCE policy gradient estimator in environments with continuous state and action spaces, linear dynamics, quadratic cost, and Gaussian noise. These simple environments allow us to derive bounds on the estimator variance in terms of the environment and noise parameters. We compare the predictions of our bounds to the empirical variance in simulation experiments.

Sébastien M. R. Arnold, Pierre-Antoine Manzagol, Reza Babanezhad et al.

Most stochastic optimization methods use gradients once before discarding them. While variance reduction methods have shown that reusing past gradients can be beneficial when there is a finite number of datapoints, they do not easily extend to the online setting. One issue is the staleness due to using past gradients. We propose to correct this staleness using the idea of implicit gradient transport (IGT) which transforms gradients computed at previous iterates into gradients evaluated at the current iterate without using the Hessian explicitly. In addition to reducing the variance and bias of our updates over time, IGT can be used as a drop-in replacement for the gradient estimate in a number of well-understood methods such as heavy ball or Adam. We show experimentally that it achieves state-of-the-art results on a wide range of architectures and benchmarks. Additionally, the IGT gradient estimator yields the optimal asymptotic convergence rate for online stochastic optimization in the restricted setting where the Hessians of all component functions are equal.

Sébastien M. R. Arnold, Chunming Wang

We introduce a novel method to compute a rank $m$ approximation of the inverse of the Hessian matrix in the distributed regime. By leveraging the differences in gradients and parameters of multiple Workers, we are able to efficiently implement a distributed approximation of the Newton-Raphson method. We also present preliminary results which underline advantages and challenges of second-order methods for large stochastic optimization problems. In particular, our work suggests that novel strategies for combining gradients provide further information on the loss surface.

Sébastien Arnold

Several recent deep neural networks experiments leverage the generalist-specialist paradigm for classification. However, no formal study compared the performance of different clustering algorithms for class assignment. In this paper we perform such a study, suggest slight modifications to the clustering procedures, and propose a novel algorithm designed to optimize the performance of of the specialist-generalist classification system. Our experiments on the CIFAR-10 and CIFAR-100 datasets allow us to investigate situations for varying number of classes on similar data. We find that our \emph{greedy pairs} clustering algorithm consistently outperforms other alternatives, while the choice of the confusion matrix has little impact on the final performance.